We used pair-wise allele sharing distances to calculate F_ST [18] among Tibetan populations and neighboring Asian groups. The two Tibetan populations exhibit the least amount of genetic differentiation from each other (F_ST = 0.004) compared to other Asian populations (HapMap Chinese [CHB] and Japanese [JPT] [19], and Buryat and Deedu Mongolians [20], [21]. Tuo Tuo River and Maduo Tibetans are similarly differentiated from the Hap Map CHB (F_ST = 0.014 and 0.012, respectively), which are commonly used for genetic comparisons (Table S1).

To determine the extent of population structure among Tibetans and neighboring populations, we used the program Admixture [22] to examine the group-specific proportion of each individual's genome (Figure 1). Each of the Tibetan populations, as well as Buryat Mongolians, Deedu Mongolians, HapMap CHB, and HapMap JPT populations, form a distinct group. As previously reported, Maduo Tibetans exhibit components associated with Han Chinese (CHB), suggesting either recent admixture or may reflect different founder populations in this group [7]. Individuals from the Tuo Tuo River population do not, however, exhibit this signal, likely reflecting the more insulated geographic location of this group (Figure 1).

We employed the same analytic strategies (iHS [23] and XP-EHH [24] statistics) used in our previous study of a Tibetan high-altitude adaptation to identify mutual targets of selection in a second linguistically distinct Tibetan population. By applying the same analytical methods in both populations, we provide further evidence for positive selection in each of two distinct Tibetan populations at the p<0.02 significance level for EPAS1, EGLN1, HMOX2, and CYP17A1 gene regions (Table 1) and further support for adaptation involving PKLR, HFE, and HBB and HBG2 genes identified in other recent studies. The first population described [7] is a group of Qinghai-Tibetans from Maduo who speak the Amdo Tibetan dialect (one of the three major Tibetan dialects spoken on the Qinghai-Tibetan Plateau); the second population examined, who speak the Kham dialect, are from the Tuo Tuo River area [13] (Figure 1). In order to identify high-altitude specific selection candidates, genomic regions with iHS significance levels at p<0.02 identified in our other Asian populations were excluded from analysis as described previously [7]. Of the selection candidate genes reported in our previous study of Maduo Tibetans [7], seven were identified at the p<0.02 significance level in Tuo Tuo River Tibetans and/or have been reported as strong selection candidates in other studies of Tibetan adaptation to altitude (Table 1).

The putatively adaptive EPAS1 genomic region is associated with [Hb] in two independent studies of high-altitude adaptation in Tibetans [2], [10]. While an extreme signal of selection near the EPAS1 gene was detected in both the Maduo and Tuo Tuo River Tibetan populations, the EPAS1 haplotype did not exhibit an association with [Hb] in Maduo Tibetans as previously reported [7], nor was there a significant association in Tuo Tuo River Tibetans (n = 36) examined here (Table S3; Figure S1). It is likely that our modest sample size yields reduced power to detect phenotype-genotype associations (Figure S2).

In our previous study of Maduo Tibetans, we identified associations between EGLN1 and PPARA selected regions and [Hb] [7]. There is no association between the EGLN1 and PPARA haplotypes and [Hb] in the 36 Tuo Tuo River Tibetans examined here (Table S3; Figure S1). We speculate that genetic heterogeneity may influence genotype-phenotype relationships as a result of the genetic admixture that was detected in Maduo but not Tuo Tuo River Tibetans (Figure 2). It will be important to test, in a larger sample, whether admixture differences underlie reduced power to detect a signal in this modest sample (Figure S2).

In order to determine whether non-genic microRNAs not previously examined as a priori candidates are contained within our top selection candidates, we examined the intersection between the top two percent of iHS and XP-EHH selection candidate regions and genomic locations that contain any of 54 hypoxia-related miRNAs [25]. Interestingly, the PPARA selection candidate region identified in our previous study contains a hypoxia-associated miRNA (Table S2) that may be involved in high-altitude response, although this region was not identified as a top selection candidate in the Tuo Tuo River Tibetans. A recent report of adaptation in Ethiopian highlanders also reports an extreme signal of selection near PPARA [26], although it is unclear whether the hypoxia-related miRNA in this region is involved in adaptation of either Tibetan or Ethiopian highland groups.

Entire mtDNA control region sequence and genotyping of present-day inhabitants of the Tibetan Plateau indicate distinct patterns of variation among Tibetan groups [16], [27]. In order to determine whether the two Tibetan populations exhibit differences in mitochondrial DNA (mtDNA) haplogroups, we genotyped 12 haplotype-defining SNPs in18 and 40 individuals from Maduo and Tuo Tuo River (Figure 1), respectively. Consistent with previously reported frequencies for Tibeto-Burman groups, the most common major mtDNA haplogroup is M (94% and 67.5% for Maduo and TTR, respectively), although a small proportion of haplogroup N is also detected in our samples. M9, which is found at elevated frequency at high-altitude inhabitants in Tibet and India [28], is predominant in both Maduo and Tuo Tuo River populations (Table 2). The sub-M haplogroups D4, M9E, and M8 are most prevalent among Maduo Tibetans, whereas M9E and G are the most common mtDNA haplogroups within the TTR sample. Haplogroup A, which exhibits greater diversity in the southern region of the Qinghai-Tibetan Plateau [17], is detected among Tibetan inhabitants of the Tuo Tuo River area (8%) and Maduo Tibetans who reside further north (7%). Haplogroup B, a major group common among Native American populations, is also present in Tuo Tuo River Tibetans (TTR: 10%). The power to detect mtDNA variants at marginal frequencies (<10%) is limited in our modest sample of mtDNA from the Maduo population, and additional sample collection will be necessary to place these samples in the context of global mtDNA variation and determine precise genetic relationships among these populations.

Selection and association signals identified in Tibetan populations may be influenced by the demographic history of these groups and by the choice of analytic methods. Despite genetic heterogeneity between Tibetan groups as shown here, several putatively adaptive genetic variants are common to Maduo and Tuo Tuo River Tibetans. Further genetic and phenotypic characterizations of physiological traits (e.g., oxygen transport, maternal/fetal responses during pregnancy) are required to determine if the remaining selection targets highlighted here are of biological significance, whether they are related to or independent of [Hb], and how combinations of such factors influence the overall physiology of native highlanders living in the Tibetan Plateau.

We extracted DNA from whole blood samples obtained from 85 highland natives (non-smokers, no chronic diseases) residing in the Tuo Tuo River township in Qinghai Province (∼4,500 m).

Participants provided written agreement as indicated by a signature or mark on a sheet of paper that described the study in their native language. Consent was obtained for all participants, and this study was approved by the Institutional Review Board at the High Altitude Medical Research Institute (Xining, Qinghai, People's Republic of China).

We employed the Affymetrix 6.0 SNP Array technology (>900,000 SNPs) to genotype 70 DNA samples at Capital Bio Corporation (Beijing, China). Default parameters for the Birdseed algorithm (version 2) were used to determine genotypes for all samples (Affymetrix, Santa Clara, CA, USA). Genotypic data were analyzed using the Affymetrix Genotyping Console 3.1 (Affymetrix) and included all autosomes but excluded the X and Y chromosomes and the mitochondrial genome.

We attempted to exclude all first-degree relatives who visited the clinic from our study. We used the ERSA software package [36] to determine genetic relatedness among all individuals examined and excluded one member of any pair exhibiting relatedness closer than second cousins. Based on these criteria, a total of 46 unrelated individuals were included in the analyses. The genotype data of the 46 individuals are available at http://jorde-lab.genetics.utah.edu/ under published data.

We performed principal components analysis on genetic distances as previously reported [21]. This analysis included two Tibetan populations from distinct regions and other Asian groups such as the HapMap CHB and JPT populations (CHB = Chinese in Beijing, China; JPT = Japanese in Tokyo, Japan). The CEU (U.S. Utah residents with ancestry from northern and western Europe) and YRI (YRI = Yoruba in Ibadan, Nigeria) HapMap populations provide context for the patterns of variation observed among these populations [19].

We had previously generated a list of genes likely related to high-altitude adaptation based on Gene Ontology and Panther Pathway categories as described in [7] and examined the intersection between these candidates and selection candidate genes identified at the p<0.02 level. Potential candidate genes identified in the mitochondrial genome and on the X chromosome were not considered for this study.

A model-based algorithm implemented in ADMIXTURE [22] was used to determine the genetic ancestries of each individual in a given number of populations without using information about population designation. To eliminate the effects of SNPs that are in linkage disequilibrium (r² = 1.0), we first filtered out SNPs that had r²>0.2 within 100 kb using PLINK [37], as recommended by the authors of ADMIXTURE.

We performed the iHS [23] and XP-EHH [24] tests of selection on phased data estimated by the Beagle software package as previously described [7]. These tests are based on extended haplotype homozygosity and measure the reduction in haplotype diversity based on the probability that, as distance from a focal SNP increases, two extended haplotypes are the same. XP-EHH compares across populations (in this case, Tuo Tuo River Tibetans and HapMap Han Chinese and Japanese); iHS compares within-population profiles based on the focal SNP's ancestral state (derived or ancestral).

We focused on the selection candidate genes contained within 200 kb regions significant at the p<0.02 level in either test. We further excluded regions where the iHS test was significant at this level in neighboring populations as previously described [7].

Hemoglobin concentration, hematocrit, and percent oxygen saturation were determined from venous blood samples using the Mindray Hematology Analyzer (BC-2300, Shenzhen, People's Republic of China) and the Pulse Oximeter (Ohmeda 3700 Pulse Oximeter, Datex-Ohmeda, Boulder, Colorado, USA), respectively.

We identified the putatively advantageous haplotypes as previously described [7] and tested whether the three-SNP allele haplotype exhibiting the most extreme iHS scores within each 200 kb genomic region were associated with [Hb] in each population and both populations combined. Stepwise linear regression (MATLAB R2010a) was used to detect significant relationships between these genotypes and [Hb].